Machine learning for fraud detection in digital banking: a systematic literature review REVIEW
This review provides a comprehensive synthesis for researchers and practitioners in digital banking fraud detection, but it is incremental as it summarizes existing work without new empirical results.
This systematic literature review synthesized 118 studies to examine machine learning's role in fraud detection in digital banking, finding that supervised methods dominate due to interpretability, while deep learning and hybrid models show transformative potential for complex fraud patterns.
This systematic literature review examines the role of machine learning in fraud detection within digital banking, synthesizing evidence from 118 peer-reviewed studies and institutional reports. Following the PRISMA guidelines, the review applied a structured identification, screening, eligibility, and inclusion process to ensure methodological rigor and transparency. The findings reveal that supervised learning methods, such as decision trees, logistic regression, and support vector machines, remain the dominant paradigm due to their interpretability and established performance, while unsupervised anomaly detection approaches are increasingly adopted to address novel fraud patterns in highly imbalanced datasets. Deep learning architectures, particularly recurrent and convolutional neural networks, have emerged as transformative tools capable of modeling sequential transaction data and detecting complex fraud typologies, though challenges of interpretability and real-time deployment persist. Hybrid models that combine supervised, unsupervised, and deep learning strategies demonstrate superior adaptability and detection accuracy, highlighting their potential as convergent solutions.